•  
  •  
 

Subject Area

Electronics and Communication Engineering

Article Type

Original Study

Abstract

At the end of the year 2019, the world was hit by a drastic pandemic known as COVID-19. The lack of treatment has prompted research in all sectors to address it. Contributions in Computer Science mainly include the development of methods for the diagnostic testing, recognition, and assessment of COVID-19 cases. The most widely used techniques in this field are data science and machine learning (ML). This paper provides a new framework for Computer Aided Diagnosis System for Covid-19 (CADS-Covid-19) using the collected blood test data from patients. CADS consists of two main stages, which are: (I) the features selection and Extraction stage and (ii) Disease Detection Stage. In the first stage, two statistical first-order features were extracted and added to the patient's blood test data to improve the classification accuracy then grey wolf Optimizer (GWO) was applied to select the most meaningful features. Then the selected features are classified as normal or COVID-19 by applying a machine learning classification algorithm, in this step the performance of K-Nearest Neighbor (KNN) and support vector machine (SVM) algorithms were compared. Therefore, KNN and SVM are the most used classifiers in the medical field, SVM got the highest accuracy percentage with more than %95

Keywords

Covid-19, artificial intelligence, patient classification, meta-heuristic, KNN, SVM, GWO, feature selection, Higher education, pandemic

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS